Codestral
Mistral's dedicated code-generation model family, optimised for fill-in-the-middle completion.
Last refreshed: 17 May 2026 · Appears in 1 active topic
Can Mistral's Codestral break GitHub Copilot's grip on European enterprise developers?
Timeline for Codestral
Bundled in Le Chat Enterprise enterprise stack
European Tech Sovereignty: Mistral ships Le Chat Enterprise and Medium 3.5- What is Mistral Codestral and how does it compare to GitHub Copilot?
- Codestral is Mistral AI's dedicated code-generation model family (22B parameters, 256K context). It supports 80+ languages and specialises in fill-in-the-middle completion. Unlike GitHub Copilot, it can be self-hosted on EU infrastructure, making it attractive for organisations with data-residency requirements.Source: Mistral AI
- Can Codestral be run locally without sending data to Mistral's servers?
- Yes. Codestral's open-weight versions can be deployed on-premises via tools like Ollama or vLLM. This is a key selling point for European public-sector and defence customers requiring air-gapped environments.Source: Mistral AI docs
- What programming languages does Codestral support?
- Codestral supports 80+ programming languages, with particular strength in Python, Java, C, C++, JavaScript, TypeScript, and Bash.Source: Mistral AI
- How does Codestral score on coding benchmarks compared to GPT-4o?
- Codestral 25.01 scores 86.6% on HumanEval. Mistral positions it as competitive with GPT-4o-class models on code-specific tasks at significantly lower cost per token.Source: Mistral AI
Background
Codestral is Mistral AI's specialised family of code-generation models, distinct from its general-purpose line. The current flagship version (Codestral 25.08) sits at 22 billion parameters with a 256K-token context window and supports over 80 programming languages including Python, Java, C++, JavaScript, and Bash. It powers fill-in-the-middle (FIM) completion, function generation, and test writing at production latency, and forms the foundation of Mistral's integrated coding stack alongside Devstral 2 and the Vibe CLI. Mistral ships Codestral alongside its broader Le Chat Enterprise platform .
Released initially in May 2024 as Mistral's first code-specific model, Codestral was retrained and upgraded through versions 25.01 and 25.08, each generation cutting latency and improving benchmark scores. Codestral 25.01 achieves 86.6% on HumanEval, placing it among the top-tier open-weight coding models globally. An accompanying Codestral Embed model provides code-specific retrieval embeddings that Mistral claims outperform OpenAI and Cohere on code-retrieval benchmarks. The 25.08 release rebranded and extended the stack into a full enterprise coding suite.
For European tech-sovereignty advocates, Codestral represents a credible EU-origin alternative to GitHub Copilot (Microsoft/OpenAI, US) and Amazon CodeWhisperer. Its open-weight design allows on-premises deployment in air-gapped environments, a critical requirement for defence, finance, and public-sector customers bound by data-residency rules. Mistral's Paris headquarters and EU entity structure give it regulatory standing that US competitors lack under the EU AI Act.
